Machine Translation with Pre-specified Target-side Words Using a Semi-autoregressive Model

Autor:	Mamoru Komachi, Tomoshige Kiyuna, Tosho Hirasawa, Seiichiro Kondo, Aomi Koyama
Rok vydání:	2021
Předmět:	Constraint (information theory) Task (computing) Machine translation Autoregressive model Computer science Speech recognition Sorting sort computer.software_genre computer Sentence Word (computer architecture)
Zdroj:	WAT@ACL/IJCNLP Scopus-Elsevier
DOI:	10.18653/v1/2021.wat-1.5
Popis:	We introduce our TMU Japanese-to-English system, which employs a semi-autoregressive model, to tackle the WAT 2021 restricted translation task. In this task, we translate an input sentence with the constraint that some words, called restricted target vocabularies (RTVs), must be contained in the output sentence. To satisfy this constraint, we use a semi-autoregressive model, namely, RecoverSAT, due to its ability (known as “forced translation”) to insert specified words into the output sentence. When using “forced translation,” the order of inserting RTVs is a critical problem. In this work, we aligned the source sentence and the corresponding RTVs using GIZA++. In our system, we obtain word alignment between a source sentence and the corresponding RTVs and then sort the RTVs in the order of their corresponding words or phrases in the source sentence. Using the model with sorted order RTVs, we succeeded in inserting all the RTVs into output sentences in more than 96% of the test sentences. Moreover, we confirmed that sorting RTVs improved the BLEU score compared with random order RTVs.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1de5617c9d13badff81d05c010ef3bba https://doi.org/10.18653/v1/2021.wat-1.5 Zobrazit plný text záznamu